HarnessAgent now supports image inputs for all harness adapters - Vercel
The AI SDK layer now accepts image inputs across every harness adapter.HarnessAgent Pass images alongside text in the standard AI SDK message format: a array mixing and parts.content{ type: 'text' }{ type: 'file' } Image input is processed by the harnesses' underlying vision models and supported…
No discussion yet. Be the first to share your thoughts!